VLM Evaluation Suite
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
VLM Evaluation Suite Hall, MME, AI2D, RWQA, SQA, POPE, MBen, MBzh, CCB, VSR, V7W
63.76Hall
40
VLM Evaluation Suite
8.25Aesthetic Appeal
8
VLM Evaluation Suite (GQA, MMB, MMBCN, MME, POPE, SQA, VQAv2, VQAText) LLaVA-NEXT-7B (test)
64.2GQA Accuracy
7